Trinity Large Thinking vs Gemma 3 4B
Trinity Large Thinking leads Gemma 3 4B on the Artificial Analysis Intelligence Index, 10.8 to 4.8, and Gemma 3 4B costs 10.7x less per output token ($0.075 vs $0.80 per million). Updated October 21, 2026; 30 benchmarks have a result for both.
Trinity Large Thinking or Gemma 3 4B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Trinity Large Thinking for a larger context window (262K against 131K tokens).
- Shared results
- 30
- Trinity Large Thinking only
- 22
- Gemma 3 4B only
- 9
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Trinity Large Thinking
Trinity Large Thinking leads, 10.8 against 4.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Trinity Large Thinking has a AA Agentic Index result, 1.0.
Directional only
Web design
Design Arena: websites
No call
Only Trinity Large Thinking has a Design Arena: websites result, 1137.
Directional only
Long documents
Listed context window
Trinity Large Thinking
Trinity Large Thinking takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 3 4B
Trinity Large Thinking $0.0006, Gemma 3 4B $0.0001 per turn.
List prices
At a glance
- Coding index
- Trinity Large Thinking not benchmarked, Gemma 3 4B not benchmarked.
- Widest category
- Agentic work, 85.1 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Trinity Large Thinking 90.1% against Gemma 3 4B 5.0%, 85.1 points apart on a 0 to 100 scale.
- Output price
- Trinity Large Thinking $0.80 against Gemma 3 4B $0.075 per million output tokens, 10.7x apart.
- Context window
- Trinity Large Thinking takes 262K tokens, Gemma 3 4B 131K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Trinity Large Thinking | Bars | Gemma 3 4B | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 30 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| LMArena WebDev | 1238 | Not measured | Only Trinity Large Thinking measured |
| AA Coding Index | 25.8 | 2.7 | Trinity Large Thinking |
| LiveCodeBench (Artificial Analysis run) | Not measured | 11.2% | Only Gemma 3 4B measured |
| SciCode | 40.6% | Not measured | Only Trinity Large Thinking measured |
| Terminal-Bench Hard (Artificial Analysis run) | 22.7% | 0.8% | Trinity Large Thinking |
| LMArena Text: coding | 1357 | 1230 | Trinity Large Thinking |
| LMArena Text: software and IT | 1362 | 1269 | Trinity Large Thinking |
| LMArena WebDev: React | 1231 | Not measured | Only Trinity Large Thinking measured |
| LMArena WebDev: HTML | 1240 | Not measured | Only Trinity Large Thinking measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 4.8 | Trinity Large Thinking |
| Epoch Capabilities Index | Not measured | 115.9 | Only Gemma 3 4B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| AA Agentic Index | 1.0 | Not measured | Only Trinity Large Thinking measured |
| τ²-Bench Telecom | 90.1% | 5.0% | Trinity Large Thinking |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 75.2% | 29.1% | Trinity Large Thinking |
| Humanity's Last Exam (Artificial Analysis run) | 15.8% | 5.3% | Trinity Large Thinking |
| GPQA Diamond (Epoch AI run) | Not measured | 23.2% | Only Gemma 3 4B measured |
| LMArena Text: hard prompts | 1342 | 1253 | Trinity Large Thinking |
| LMArena Text: expert | 1359 | 1223 | Trinity Large Thinking |
| LMArena Text: hard prompts in English | 1356 | 1253 | Trinity Large Thinking |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 12.7 | Only Gemma 3 4B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 12.7% | Only Gemma 3 4B measured |
| OTIS Mock AIME | Not measured | 7.5% | Only Gemma 3 4B measured |
| LMArena Text: math | 1365 | 1239 | Trinity Large Thinking |
| LMArena Text: mathematical work | 1350 | 1256 | Trinity Large Thinking |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 57.9% | Not measured | Only Trinity Large Thinking measured |
| CorpFin (Vals AI) | 54.7% | Not measured | Only Trinity Large Thinking measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 41.7% | Only Gemma 3 4B measured |
| LMArena Text: science | 1355 | 1306 | Trinity Large Thinking |
| LMArena Text: medicine and healthcare | 1349 | 1342 | Trinity Large Thinking |
| LMArena Text: legal and government | 1345 | 1327 | Trinity Large Thinking |
| LMArena Text: business and finance | 1329 | 1311 | Trinity Large Thinking |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| Design Arena: websites | 1137 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: UI components | 1045 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: game dev | 1079 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: data viz | 1098 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: 3D | 1082 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: all code categories | 1117 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: SVG | 1017 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: ASCII art | 1041 | Not measured | Only Trinity Large Thinking measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| IFBench | 56.3% | 28.3% | Trinity Large Thinking |
| Long context reasoning (AA-LCR) | 38.0% | 6.7% | Trinity Large Thinking |
| DTBench | Not measured | 50.9% | Only Gemma 3 4B measured |
| LMCA | Not measured | 2.8% | Only Gemma 3 4B measured |
| Surface Evolver Bench | 15.6% | Not measured | Only Trinity Large Thinking measured |
| LMArena Text | 1340 | 1291 | Trinity Large Thinking |
| LMArena Text: instruction following | 1326 | 1239 | Trinity Large Thinking |
| LMArena Text: creative writing | 1308 | 1270 | Trinity Large Thinking |
| LMArena Text: English | 1356 | 1300 | Trinity Large Thinking |
| LMArena Text: non-English | 1325 | 1273 | Trinity Large Thinking |
| LMArena Text: Chinese | 1371 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: German | 1356 | 1281 | Trinity Large Thinking |
| LMArena Text: Japanese | 1312 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Korean | 1306 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: French | 1366 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Spanish | 1327 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Russian | 1338 | 1294 | Trinity Large Thinking |
| LMArena Text: Polish | 1312 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: multi-turn | 1320 | 1255 | Trinity Large Thinking |
| LMArena Text: longer queries | 1318 | 1273 | Trinity Large Thinking |
| LMArena Text: writing and language | 1317 | 1288 | Trinity Large Thinking |
| LMArena Text: entertainment and media | 1296 | 1233 | Trinity Large Thinking |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Trinity Large Thinking | Gemma 3 4B | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 3 4B costs less
Repository review
50K input + 3K output tokens
Gemma 3 4B costs less
Agent loop
200K input + 10K output tokens
Gemma 3 4B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Arcee AI Trinity Large Thinking | Google Gemma 3 4B |
|---|---|---|
| Maker | Arcee AI | |
| Weights | Open weights | Open weights |
| Released | April 1, 2026 | March 13, 2025 |
| Context window | 262K | 131K |
| Input $/Mtok | $0.25 | $0.045 |
| Output $/Mtok | $0.80 | $0.075 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Trinity Large Thinking better than Gemma 3 4B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Trinity Large Thinking for a larger context window (262K against 131K tokens).
Which is cheaper, Trinity Large Thinking or Gemma 3 4B?
Trinity Large Thinking costs $0.25 per million input tokens and $0.80 per million output tokens; Gemma 3 4B costs $0.045 and $0.075. Cost per solved task is known for neither of them.
Which has the bigger context window, Trinity Large Thinking or Gemma 3 4B?
Trinity Large Thinking, with 262K tokens against 131K.
How many benchmarks is the Trinity Large Thinking vs Gemma 3 4B comparison based on?
30 benchmarks have a result for both models as of October 21, 2026. Trinity Large Thinking's coding index rests on 1 independent benchmark and Gemma 3 4B's on 0. Where only one model has a result, the page says so instead of naming a winner.